多数据集拼接后执行K-Means聚类报AttributeError问题求助

问题说明 #

• 现有5份多字段的不同类型电容温度实验数据，计划对拼接后的全量数据集执行K-Means聚类分析
• 完成所有数据集拼接后运行代码，持续触发报错：AttributeError: 'NoneType' object has no attribute 'split'

相关资源 #

• 实验数据集：电容温度实验数据
• 运行截图：报错截图1、报错截图2、报错截图3
• 原始代码：Python分析代码

原始复现代码 #

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
import plotly.express as px

# 读取温度实验数据
Cap_80=pd.read_csv(r"C:\Users\User\Documents\CapacitorEXP\Temp_Cap_2200\data0203_200uf_80deg.csv",encoding='unicode_escape')

Cap_90=pd.read_csv(r"C:\Users\User\Documents\CapacitorEXP\Temp_Cap_2200\data0303_2200uf_90deg.csv",encoding='unicode_escape')

Cap_100=pd.read_csv(r"C:\Users\User\Documents\CapacitorEXP\Temp_Cap_2200\data0803_200uf_110deg.csv",encoding='unicode_escape')

Cap_110=pd.read_csv(r"C:\Users\User\Documents\CapacitorEXP\Temp_Cap_2200\data0803_2200uf_110deg.csv",encoding='unicode_escape')

Cap_120=pd.read_csv(r"C:UsersUserDocumentsCapacitorEXPTemp_Cap_2200data1803_2200uf_120deg.csv",cap_120encoding='unicode_escape')


# 提取每份数据集的目标列
df1 = pd.DataFrame(Cap_80.iloc[:,5:9].reset_index(drop=True))
                   
df2 = pd.DataFrame(Cap_90.iloc[:,5:9].reset_index(drop=True))

df3 = pd.DataFrame(Cap_100.iloc[:,5:9].reset_index(drop=True))

df4 = pd.DataFrame(Cap_110.iloc[:,5:9].reset_index(drop=True))
                   
df5 = pd.DataFrame(Cap_120.iloc[:,5:9].reset_index(drop=True))

# 合并所有数据集
df = (df1, df2, df3, df4, df5)
data = pd.concat(df)

# 用肘部法则确定最优k值
wcss=[]
for i in range(1,7):
kmeans = KMeans(i)
kmeans.fit(data)
wcss_iter = kmeans.inertia_
wcss.append(wcss_iter)

number_clusters = range(1,7)
plt.plot(number_clusters,wcss)
plt.title('The Elbow title')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')

k_means_optimum = KMeans(n_clusters = 2, init = 'k-means++',  random_state=42)
y = k_means_optimum.fit_predict(data)
print(y)

完整报错栈 #

AttributeError                            Traceback (most recent call last)
<ipython-input-14-d1d8a96c4bce> in <module>
      1 k_means_optimum = KMeans(n_clusters = 3, init = 'k-means++',  random_state=42)
----> 2 y = k_means_optimum.fit_predict(data)
      3 print(y)

~\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py in fit_predict(self, X, y, sample_weight)
   1097             Index of the cluster each sample belongs to.
   1098         """
-> 1099         return self.fit(X, sample_weight=sample_weight).labels_
   1100 
   1101     def fit_transform(self, X, y=None, sample_weight=None):

~\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py in fit(self, X, y, sample_weight)
   1043         for seed in seeds:
   1044             # run a k-means once
-> 1045             labels, inertia, centers, n_iter_ = kmeans_single(
   1046                 X, sample_weight, self.n_clusters, max_iter=self.max_iter,
   1047                 init=init, verbose=self.verbose, tol=tol,

~\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py in _kmeans_single_elkan(X, sample_weight, n_clusters, max_iter, init, verbose, x_squared_norms, random_state, tol, n_threads)
    432 
    433     for i in range(max_iter):
--> 434         elkan_iter(X, sample_weight, centers, centers_new, weight_in_clusters,
    435                    center_half_distances, distance_next_center, upper_bounds,
    436                    lower_bounds, labels, center_shift, n_threads)

sklearn\cluster\_k_means_elkan.pyx in sklearn.cluster._k_means_elkan.elkan_iter_chunked_dense()

~\anaconda3\lib\site-packages\threadpoolctl.py in __init__(self, limits, user_api)
    169             self._check_params(limits, user_api)
    170 
--> 171         self._original_info = self._set_threadpool_limits()
    172 
    173     def __enter__(self):

~\anaconda3\lib\site-packages\threadpoolctl.py in _set_threadpool_limits(self)
    266             return None
    267 
--> 268         modules = _ThreadpoolInfo(prefixes=self._prefixes,
    269                                   user_api=self._user_api)
    270         for module in modules:

~\anaconda3\lib\site-packages\threadpoolctl.py in __init__(self, user_api, prefixes, modules)
    338 
    339             self.modules = []
--> 340             self._load_modules()
    341             self._warn_if_incompatible_openmp()
    342         else:

~\anaconda3\lib\site-packages\threadpoolctl.py in _load_modules(self)
    371             self._find_modules_with_dyld()
    372         elif sys.platform == "win32":
--> 373             self._find_modules_with_enum_process_module_ex()
    374         else:
    375             self._find_modules_with_dl_iterate_phdr()

~\anaconda3\lib\site-packages\threadpoolctl.py in _find_modules_with_enum_process_module_ex(self)
    483 
    484                 # Store the module if it is supported and selected
--> 485                 self._make_module_from_path(filepath)
    486         finally:
    487             kernel_32.CloseHandle(h_process)

~\anaconda3\lib\site-packages\threadpoolctl.py in _make_module_from_path(self, filepath)
    513             if prefix in self.prefixes or user_api in self.user_api:
    514                 module_class = globals()[module_class]
--> 515                 module = module_class(filepath, prefix, user_api, internal_api)
    516                 self.modules.append(module)
    517 

~\anaconda3\lib\site-packages\threadpoolctl.py in __init__(self, filepath, prefix, user_api, internal_api)
    604         self.internal_api = internal_api
    605         self._dynlib = ctypes.CDLL(filepath, mode=_RTLD_NOLOAD)
--> 606         self.version = self.get_version()
    607         self.num_threads = self.get_num_threads()
    608         self._get_extra_info()

~\anaconda3\lib\site-packages\threadpoolctl.py in get_version(self)
    644                              lambda: None)
    645         get_config.restype = ctypes.c_char_p
--> 646         config = get_config().split()
    647         if config[0] == b"OpenBLAS":
    648             return config[1].decode("utf-8")

AttributeError: 'NoneType' object has no attribute 'split'

错误修复步骤 #

1. 先修复代码本身的语法与逻辑错误 #

• 修复Cap_120文件读取错误：原代码路径丢失反斜杠，且参数名错误多写了cap_120前缀，修正为：

Cap_120=pd.read_csv(r"C:\Users\User\Documents\CapacitorEXP\Temp_Cap_2200\data1803_2200uf_120deg.csv",encoding='unicode_escape')

• 修复肘部法则循环缩进错误：for循环下的代码需统一缩进4空格，否则循环逻辑不生效：

for i in range(1,7):
    kmeans = KMeans(i)
    kmeans.fit(data)
    wcss_iter = kmeans.inertia_
    wcss.append(wcss_iter)

• 新增数据清洗逻辑：KMeans不支持非数值、空值输入，拼接完数据后需先做清洗：

data = pd.concat(df).reset_index(drop=True)
# 删除空值，统一转为浮点型
data = data.dropna().astype(float)

2. 修复split属性报错 #

该报错是Anaconda Windows环境下常见的依赖兼容问题，由threadpoolctl库与OpenBLAS版本不匹配导致，按优先级选以下一种方案即可：

• 方案1（优先尝试）：在所有import语句最开头添加环境变量配置，绕过线程池版本检测：

import os
os.environ["OPENBLAS_NUM_THREADS"] = "1"

• 方案2：如果方案1无效，在Anaconda终端执行命令升级不兼容依赖，升级完成后重启Python内核再运行：

pip install --upgrade threadpoolctl numpy scikit-learn

内容的提问来源于stack exchange，提问作者sololurd